Greetings!
This tutorial illustrates how to interpret the more advanced output and to set different prior specifications in performing Bayesian regression analyses in JASP (JASP Team, 2020). We explain various options in the control panel and introduce such concepts as Bayesian model averaging, posterior model probability, prior model probability, inclusion Bayes factor, and posterior exclusion probability. After the tutorial, we expect readers can deeply comprehend the Bayesian regression and perform it to answer substantive research questions.
For readers who need fundamentals of JASP, we recommend reading JASP for beginners. If readers need nuts and bolts of Bayesian analyses in JASP, we suggest following JASP for Bayesian analyses with default priors. The current tutorial assumes that readers are equipped with the knowledge necessary for advanced Bayesian regression analysis.
Since we continuously improve the tutorials, let us know if you discover mistakes, or if you have additional resources we can refer to. If you want to be the first to be informed about updates, follow Rens on Twitter.
Let’s get started!
Heo, I., & Van de Schoot, R. (2020, September 14). Advanced Bayesian regression in JASP. Zenodo. https://doi.org/10.5281/zenodo.3991326
We will use a phd-delay dataset (Van de Schoot, 2020) from Van de Schoot, Yerkes, Mouw, and Sonneveld (2013). To download the dataset, click here.
The dataset is based on a study that asks Ph.D. recipients how long it took them to complete their Ph.D. projects (n = 333). It turned out that the Ph.D. recipients took an average of 59.8 months to finish their Ph.D. trajectory.
For more information on the sample, instruments, methodology, and research context, we refer interested readers to the paper (see references). A brief description of the variables in the dataset follows. The variable names in the table below will be used in the tutorial, henceforth.
| Variable name | Description |
|---|---|
| B3_difference_extra | The difference between planned and actual project time in months |
| E4_having_child | Whether there are any children under the age of 18 living in the household (0 = no, 1 = yes) |
| E21_sex | Respondents’ gender (0 = female, 1 = male) |
| E22_Age | Respondents’ age |
| E22_Age_Squared | Respondents’ age-squared |
Van de Schoot, R. (2020). PhD-delay Dataset for Online Stats Training [Data set]. Zenodo. https://doi.org/10.5281/zenodo.3999424
| Age | Default (JZS with r = 0.354) | JZS with r = 0.001 | JZS with r = 0.1 | JZS with r = 10 | JZS with r = 1000 |
|---|---|---|---|---|---|
| Posterior mean | 2.533 | 1.711 | 2.315 | 3.172e-13 | 0.000 |
| Posterior standard deviation | 0.586 | 0.853 | 0.560 | 2.025e-7 | 0.000 |
| Age-squared | Default (JZS with r = 0.354) | JZS with r = 0.001 | JZS with r = 0.1 | JZS with r = 10 | JZS with r = 1000 |
|---|---|---|---|---|---|
| Posterior mean | -0.025 | -0.017 | -0.022 | -3.082e-15 | 0.000 |
| Posterior standard deviation | 0.006 | 0.008 | 0.006 | 2.115e-9 | 0.000 |
| \(Age\) | Default (JZS with r = 0.354) | User-specified (JZS with r = 0.001) |
|---|---|---|
| Posterior mean | 2.533 | 1.711 |
| Posterior standard deviation | 0.586 | 0.853 |
| 95% credible interval | [1.325, 3.480] | [-0.031, 2.760] |
| \(Age^{2}\) | Default (JZS with r = 0.354) | User-specified (JZS with r = 0.001) |
|---|---|---|
| Posterior mean | -0.025 | -0.017 |
| Posterior standard deviation | 0.006 | 0.008 |
| 95% credible interval | [-0.037, -0.015] | [-0.028, 3.777e-4] |
| \(Age\) | Default (JZS with r = 0.354) | User-specified (JZS with r = 0.001) |
|---|---|---|
| \(BF_{inclusion}\) | 513.165 | 8.088 |
| \(Age^{2}\) | Default (JZS with r = 0.354) | User-specified (JZS with r = 0.001) |
|---|---|---|
| \(BF_{inclusion}\) | 404.684 | 7.989 |
Andraszewicz, S., Scheibehenne, B., Rieskamp, J., Grasman, R., Verhagen, J., & Wagenmakers, E. J. (2015). An introduction to Bayesian hypothesis testing for management research. Journal of Management, 41(2), 521-543. https://doi.org/10.1177/0149206314560412
Hinne, M., Gronau, Q. F., van den Bergh, D., & Wagenmakers, E. J. (2020). A conceptual introduction to Bayesian model averaging. Advances in Methods and Practices in Psychological Science, 3(2), 200-215. https://doi.org/10.1177/2515245919898657
Hoeting, J. A., Madigan, D., Raftery, A. E., & Volinsky, C. T. (1999). Bayesian model averaging: a tutorial. Statistical science, 382-401.
JASP Team (2020). JASP (Version 0.13.1)[Computer software].
Kass, R. E., & Raftery, A. E. (1995). Bayes factors. Journal of the american statistical association, 90(430), 773-795.
Kruschke, J. (2014). Doing Bayesian data analysis: A tutorial with R, JAGS, and Stan (2nd ed.). Academic Press.
Liang, F., Paulo, R., Molina, G., Clyde, M. A., & Berger, J. O. (2008). Mixtures of g priors for Bayesian variable selection. Journal of the American Statistical Association, 103(481), 410-423. https://doi.org/10.1198/016214507000001337
Van de Schoot, R. (2020). PhD-delay Dataset for Online Stats Training [Data set]. Zenodo. https://doi.org/10.5281/zenodo.3999424
Van de Schoot, R., Kaplan, D., Denissen, J., Asendorpf, J. B., Neyer, F. J., & Van Aken, M. A. (2014). A gentle introduction to Bayesian analysis: Applications to developmental research. Child development, 85(3), 842-860. https://doi.org/10.1111/cdev.12169
Van de Schoot, R., Yerkes, M. A., Mouw, J. M., & Sonneveld, H. (2013). What took them so long? Explaining PhD delays among doctoral candidates. PloS one, 8(7), e68839. https://doi.org/10.1371/journal.pone.0068839
Van den Bergh, D., Clyde, M. A., Raj, A., de Jong, T., Gronau, Q. F., Ly, A., & Wagenmakers, E. J. (2020). A Tutorial on Bayesian Multi-Model Linear Regression with BAS and JASP. https://doi.org/10.31234/osf.io/pqju6
Van Erp, S., Mulder, J., & Oberski, D. L. (2018). Prior sensitivity analysis in default Bayesian structural equation modeling. Psychological Methods, 23(2), 363. https://doi.org/10.1037/met0000162